Files
lerobot_piper/lerobot/common/datasets/push_dataset_to_hub/utils.py
2024-05-15 12:13:09 +02:00

54 lines
1.8 KiB
Python

#!/usr/bin/env python
# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from concurrent.futures import ThreadPoolExecutor
from pathlib import Path
import numpy
import PIL
import torch
def concatenate_episodes(ep_dicts):
data_dict = {}
keys = ep_dicts[0].keys()
for key in keys:
if torch.is_tensor(ep_dicts[0][key][0]):
data_dict[key] = torch.cat([ep_dict[key] for ep_dict in ep_dicts])
else:
if key not in data_dict:
data_dict[key] = []
for ep_dict in ep_dicts:
for x in ep_dict[key]:
data_dict[key].append(x)
total_frames = data_dict["frame_index"].shape[0]
data_dict["index"] = torch.arange(0, total_frames, 1)
return data_dict
def save_images_concurrently(imgs_array: numpy.array, out_dir: Path, max_workers: int = 4):
out_dir = Path(out_dir)
out_dir.mkdir(parents=True, exist_ok=True)
def save_image(img_array, i, out_dir):
img = PIL.Image.fromarray(img_array)
img.save(str(out_dir / f"frame_{i:06d}.png"), quality=100)
num_images = len(imgs_array)
with ThreadPoolExecutor(max_workers=max_workers) as executor:
[executor.submit(save_image, imgs_array[i], i, out_dir) for i in range(num_images)]